LLM API pricing
Same model. Better price.
Search 272 LLMs across 34 providers. Open a model to price your workload.
Standard list prices in USD. Last price change Oct 28, 2026. How we collect and rank prices.
Find your model
Sort and filter in the column headings. Prices use a 3:1 input/output blend; open a model for your own volume. GPQA: share of graduate-level science questions answered correctly in Epoch AI's runs (CC BY 4.0), best reasoning setting.
| Developer | |||||||
|---|---|---|---|---|---|---|---|
| gpt-oss-120b | OpenAI | 18 | W&B Inference (CoreWeave) | $0.03 | $0.17 | 76% | 131K |
| GLM-5.2 | Z.ai GLM | 13 | DeepInfra | $0.75 | $2.40 | 92% | 1M |
| Llama-3.3-70B-Instruct | Meta Llama | 13 | Nebius Token Factory | $0.13 | $0.40 | 47% | 131K |
| GLM-5.3 | Z.ai GLM | 12 | DeepInfra | $0.90 | $4.00 | 91% | 1M |
| GLM-5.3-Flash | Z.ai GLM | 11 | Z.ai | $0.15 | $0.50 | 90% | 1M |
| DeepSeek V4 Flash 0731 | DeepSeek | 10 | DeepInfra | $0.08 | $0.18 | 91% | 1M |
| gpt-oss-20b | OpenAI | 10 | W&B Inference (CoreWeave) | $0.03 | $0.13 | 61% | 131K |
| Llama-3.1-8B-Instruct | Meta Llama | 10 | Novita AI | $0.02 | $0.05 | 27% | 131K |
| Kimi K3 | Moonshot AI Kimi | 9 | SiliconFlow | $2.70 | $13.50 | 93% | 1M |
| DeepSeek V4 Pro 0813 | DeepSeek | 8 | DeepInfra | $1.30 | $2.60 | 92% | 1M |
| DeepSeek-R1 | DeepSeek | 8 | SiliconFlow | $0.50 | $2.18 | 69% | 164K |
| DeepSeek-V3 | DeepSeek | 8 | SiliconFlow | $0.25 | $1.00 | 57% | 164K |
| DeepSeek-V3.2 | DeepSeek | 8 | DeepInfra | $0.26 | $0.38 | - | 164K |
| DeepSeek-V4.1-Flash | DeepSeek | 8 | DeepInfra | $0.14 | $0.42 | 90% | 1M |
| Kimi K2.6 | Moonshot AI Kimi | 8 | W&B Inference (CoreWeave) | $0.65 | $3.41 | 91% | 262K |
| Kimi K2.7 Code | Moonshot AI Kimi | 8 | DeepInfra | $0.68 | $3.40 | 88% | 262K |
| DeepSeek-V3.1 | DeepSeek | 7 | DeepInfra | $0.25 | $0.95 | - | 164K |
| DeepSeek-V4-Flash | DeepSeek | 7 | DeepInfra | $0.09 | $0.18 | - | 1M |
| Gemma 4 26B A4B IT | Google Gemini and Gemma | 7 | DeepInfra | $0.07 | $0.34 | 73% | 262K |
| GLM-5.1 | Z.ai GLM | 7 | DeepInfra | $1.05 | $3.50 | 90% | 205K |
| Kimi K2.5 | Moonshot AI Kimi | 7 | DeepInfra | $0.45 | $2.25 | - | 262K |
| Llama 3.2 3B Instruct | Meta Llama | 7 | Lambda | $0.015 | $0.025 | - | 131K |
| Llama 4 Scout 17B 16E Instruct | Meta Llama | 7 | Lambda | $0.05 | $0.10 | 52% | 10.5M |
| llama-3.1-70b-instruct | Meta Llama | 7 | Nebius Token Factory | $0.13 | $0.40 | 44% | 131K |
| MiniMax-M3 | MiniMax | 7 | W&B Inference (CoreWeave) | $0.23 | $0.96 | 91% | 1M |
| Qwen3 32B | Alibaba Qwen | 7 | DeepInfra | $0.08 | $0.28 | 66% | 131K |
| Qwen3.8 27B | Alibaba Qwen | 7 | DeepInfra | $0.40 | $3.00 | - | 1M |
| DeepSeek V4 Pro | DeepSeek | 6 | DeepInfra | $1.30 | $2.60 | 91% | 1M |
| DeepSeek V4.1 Flash 1017 | DeepSeek | 6 | DeepInfra | $0.14 | $0.42 | - | 1M |
| DeepSeek-R1-0528 | DeepSeek | 6 | Lambda | $0.20 | $0.60 | 76% | 164K |
| deepseek-r1-distill-llama-70b | DeepSeek | 6 | DeepInfra | $0.20 | $0.60 | 56% | 131K |
| Gemma 4 31B IT | Google Gemini and Gemma | 6 | W&B Inference (CoreWeave) | $0.10 | $0.34 | 76% | 262K |
| Llama 4 Maverick 17B 128E Instruct FP8 | Meta Llama | 6 | Lambda | $0.05 | $0.10 | 67% | 1M |
| Qwen2.5-72B-Instruct | Alibaba Qwen | 6 | Nebius Token Factory | $0.13 | $0.40 | 49% | 128K |
| Qwen3 235B A22B Instruct 2507 | Alibaba Qwen | 6 | DeepInfra | $0.09 | $0.55 | - | 262K |
| Qwen3.6 35B-A3B | Alibaba Qwen | 6 | DeepInfra | $0.10 | $0.95 | 85% | 262K |
| Claude Fable 5 | Anthropic Claude | 5 | Anthropic | $10.00 | $50.00 | 86% | 1M |
| Claude Haiku 4.5 | Anthropic Claude | 5 | Anthropic | $1.00 | $5.00 | - | 200K |
| Claude Opus 4.7 | Anthropic Claude | 5 | Anthropic | $5.00 | $25.00 | 90% | 1M |
| Claude Opus 4.8 | Anthropic Claude | 5 | Anthropic | $5.00 | $25.00 | 91% | 1M |
| Claude Opus 5 | Anthropic Claude | 5 | Anthropic | $5.00 | $25.00 | 94% | 1M |
| Claude Sonnet 4.6 | Anthropic Claude | 5 | Anthropic | $3.00 | $15.00 | 83% | 1M |
| Claude Sonnet 5 | Anthropic Claude | 5 | Anthropic | $2.00 | $10.00 | 91% | 1M |
| Deepseek R1 Distill Qwen 32B | DeepSeek | 5 | Nscale | $0.15 | $0.15 | 64% | 131K |
| deepseek-v3-0324 | DeepSeek | 5 | Lambda | $0.20 | $0.60 | 68% | 164K |
| Gemma-3-27b-it | Google Gemini and Gemma | 5 | DeepInfra | $0.08 | $0.16 | 48% | 131K |
| GLM-4.6 | Z.ai GLM | 5 | DeepInfra | $0.50 | $2.00 | - | 205K |
| GLM-4.7 | Z.ai GLM | 5 | DeepInfra | $0.40 | $1.75 | 83% | 205K |
| GLM-5 | Z.ai GLM | 5 | DeepInfra | $0.60 | $2.08 | 88% | 205K |
| Llama 3.2 11B Vision Instruct | Meta Llama | 5 | Lambda | $0.015 | $0.025 | - | 131K |
| Llama 3.2 1B Instruct | Meta Llama | 5 | Novita AI | $0.02 | $0.02 | - | 131K |
| Qwen2.5 Coder 32B Instruct | Alibaba Qwen | 5 | Lambda | $0.05 | $0.10 | - | 131K |
| Qwen3.5 397B-A17B | Alibaba Qwen | 5 | DeepInfra | $0.45 | $3.00 | 86% | 262K |
| Qwen3.8 2.4T A95B | Alibaba Qwen | 5 | DeepInfra | $2.00 | $6.00 | - | 1M |
| Qwq 32B | Alibaba Qwen | 5 | Nscale | $0.18 | $0.20 | 65% | 131K |
| Claude Fable 5.1 | Anthropic Claude | 4 | Anthropic | $10.00 | $50.00 | - | 1M |
| Claude Haiku 5.5 | Anthropic Claude | 4 | Anthropic | $0.10 | $0.50 | 90% | 1M |
| Claude Opus 4.5 | Anthropic Claude | 4 | Anthropic | $5.00 | $25.00 | - | 200K |
| Claude Opus 4.6 | Anthropic Claude | 4 | Anthropic | $5.00 | $25.00 | 88% | 1M |
| Claude Opus 5.5 | Anthropic Claude | 4 | Anthropic | $4.00 | $20.00 | 91% | 1M |
| Claude Sonnet 5.5 | Anthropic Claude | 4 | Anthropic | $2.00 | $10.00 | 96% | 1M |
| DeepSeek V4 Flash Vision Exp | DeepSeek | 4 | DeepSeek | $0.30 | $1.20 | - | 1M |
| DeepSeek-V3.1-Terminus | DeepSeek | 4 | DeepInfra | $0.27 | $1.00 | - | 164K |
| Gemini 2.5 Flash | Google Gemini and Gemma | 4 | Oracle Cloud Generative AI | $0.15 | $0.60 | - | 1M |
| GLM-4.5 | Z.ai GLM | 4 | DeepInfra | $0.40 | $1.60 | - | 131K |
| GLM-4.5-Air | Z.ai GLM | 4 | Novita AI | $0.13 | $0.85 | - | 131K |
| GLM-4.7-Flash | Z.ai GLM | 4 | DeepInfra | $0.06 | $0.40 | 61% | 203K |
| GPT-5 | OpenAI | 4 | OpenAI | $1.25 | $10.00 | - | 272K |
| GPT-5 Mini | OpenAI | 4 | OpenAI | $0.25 | $2.00 | - | 272K |
| GPT-5 Nano | OpenAI | 4 | OpenAI | $0.05 | $0.40 | - | 272K |
| Kimi K2 Instruct | Moonshot AI Kimi | 4 | DeepInfra | $0.50 | $2.00 | - | 131K |
| Llama Guard 3 8B | Meta Llama | 4 | Nebius Token Factory | $0.02 | $0.06 | - | 131K |
| llama-3.1-405b-instruct | Meta Llama | 4 | Nebius Token Factory | $1.00 | $3.00 | - | 131K |
| llama3-70b-instruct | Meta Llama | 4 | Novita AI | $0.51 | $0.74 | - | 8K |
| llama3-8b-instruct | Meta Llama | 4 | DeepInfra | $0.03 | $0.06 | - | 8K |
| MiniMax-M2.5 | MiniMax | 4 | FriendliAI | $0.30 | $1.20 | - | 205K |
| MiniMax-M2.7 | MiniMax | 4 | DeepInfra | $0.25 | $1.00 | - | 205K |
| mistral-nemo-instruct-2407 | Mistral AI | 4 | DeepInfra | $0.019 | $0.03 | - | 131K |
| Qwen2.5-7B-Instruct | Alibaba Qwen | 4 | SiliconFlow | $0.05 | $0.05 | 35% | 33K |
| qwen2.5-vl-72b-instruct | Alibaba Qwen | 4 | Nebius Token Factory | $0.25 | $0.75 | - | 128K |
| Qwen3 VL 30B A3B Instruct | Alibaba Qwen | 4 | DeepInfra | $0.15 | $0.60 | - | 262K |
| Qwen3-14B | Alibaba Qwen | 4 | Nebius Token Factory | $0.08 | $0.24 | 64% | 131K |
| Qwen3-Coder-480B-A35B-Instruct | Alibaba Qwen | 4 | SiliconFlow | $0.25 | $1.00 | - | 262K |
| qwen3-next-80b-a3b-thinking | Alibaba Qwen | 4 | Nebius Token Factory | $0.15 | $1.20 | - | 262K |
| Qwen3.5 122B-A10B | Alibaba Qwen | 4 | SiliconFlow | $0.26 | $2.08 | - | 262K |
| Qwen3.5 27B | Alibaba Qwen | 4 | SiliconFlow | $0.25 | $2.00 | - | 262K |
| Qwen3.5 35B-A3B | Alibaba Qwen | 4 | DeepInfra | $0.14 | $1.00 | 83% | 262K |
| Qwen3.6 27B | Alibaba Qwen | 4 | SiliconFlow | $0.30 | $3.20 | 86% | 262K |
| Qwen3.7 Max | Alibaba Qwen | 4 | Novita AI | $1.25 | $3.75 | 91% | 1M |
| Qwen3.8 Flash | Alibaba Qwen | 4 | DeepInfra | $0.113 | $0.382 | - | 1M |
| Qwen3.8 Max | Alibaba Qwen | 4 | DeepInfra | $1.65 | $4.95 | 93% | 1M |
| Claude Mythos 5 | Anthropic Claude | 3 | Anthropic | $10.00 | $50.00 | - | 1M |
| Claude Sonnet 4.5 | Anthropic Claude | 3 | Anthropic | $3.00 | $15.00 | - | 200K |
| claude-3-7-sonnet | Anthropic Claude | 3 | Replicate | $3.00 | $15.00 | - | 200K |
| deepseek-r1-distill-qwen-14b | DeepSeek | 3 | Nscale | $0.07 | $0.07 | 45% | 131K |
| Gemini 2.5 Pro | Google Gemini and Gemma | 3 | Google Gemini API | $1.25 | $10.00 | 85% | 1M |
| Gemini 3.1 Flash Lite | Google Gemini and Gemma | 3 | Google Gemini API | $0.25 | $1.50 | 82% | 1M |
| Gemini 3.5 Flash | Google Gemini and Gemma | 3 | Google Gemini API | $1.50 | $9.00 | 93% | 1M |
| Gemini 3.7 Flash | Google Gemini and Gemma | 3 | Google Gemini API | $0.75 | $3.75 | 95% | 1M |
| Gemma 3 12B IT | Google Gemini and Gemma | 3 | Novita AI | $0.05 | $0.10 | 39% | 131K |
| GLM-4.5V | Z.ai GLM | 3 | Z.ai | $0.60 | $1.80 | - | 131K |
| GLM-5V-Turbo | Z.ai GLM | 3 | Z.ai | $1.20 | $4.00 | - | 205K |
| GPT-4.1 | OpenAI | 3 | OpenAI | $2.00 | $8.00 | - | 1M |
| GPT-4.1 mini | OpenAI | 3 | OpenAI | $0.40 | $1.60 | - | 1M |
| GPT-4o | OpenAI | 3 | OpenAI | $2.50 | $10.00 | - | 128K |
| GPT-4o mini | OpenAI | 3 | OpenAI | $0.15 | $0.60 | - | 128K |
| GPT-5.4 | OpenAI | 3 | OpenAI | $2.50 | $15.00 | - | 1.1M |
| GPT-5.5 | OpenAI | 3 | OpenAI | $5.00 | $30.00 | 91% | 1.1M |
| GPT-5.6 Luna | OpenAI | 3 | OpenAI | $0.20 | $1.20 | 92% | 922K |
| GPT-5.6 Sol | OpenAI | 3 | OpenAI | $4.00 | $20.00 | 93% | 922K |
| GPT-5.6 Terra | OpenAI | 3 | OpenAI | $2.00 | $12.00 | 93% | 922K |
| GPT-6 Astra | OpenAI | 3 | OpenAI | $10.00 | $50.00 | 96% | 922K |
| GPT-6 Luna | OpenAI | 3 | OpenAI | $0.10 | $0.50 | 90% | 922K |
| GPT-6 Sol | OpenAI | 3 | OpenAI | $2.00 | $10.00 | 94% | 922K |
| GPT-6.1 Sol | OpenAI | 3 | OpenAI | $2.00 | $10.00 | 95% | 1M |
| GPT-6.1 Terra | OpenAI | 3 | OpenAI | $1.00 | $5.00 | - | 922K |
| Grok 4.20 (Non-Reasoning) | xAI Grok | 3 | xAI | $1.25 | $2.50 | - | 2M |
| Grok 4.20 (Reasoning) | xAI Grok | 3 | xAI | $1.25 | $2.50 | - | 2M |
| Grok 4.3 | xAI Grok | 3 | xAI | $1.25 | $2.50 | 89% | 1M |
| Grok 4.6 | xAI Grok | 3 | xAI | $2.00 | $6.00 | 94% | 524K |
| Grok 4.7 | xAI Grok | 3 | xAI | $2.00 | $6.00 | 93% | 524K |
| Hy3 | - | 3 | SiliconFlow | $0.132 | $0.528 | - | 262K |
| Inkling | - | 3 | DeepInfra | $0.95 | $4.05 | 88% | 1M |
| Kimi K2 Thinking | Moonshot AI Kimi | 3 | Fireworks AI | $0.60 | $2.50 | - | 262K |
| llama-2-70b-chat | Meta Llama | 3 | Fireworks AI | $0.90 | $0.90 | - | 4K |
| llama-3-2-90b-vision-instruct | Meta Llama | 3 | Fireworks AI | $0.90 | $0.90 | 41% | 131K |
| minimax-m2 | MiniMax | 3 | Fireworks AI | $0.30 | $1.20 | - | 1M |
| minimax-m2.1 | MiniMax | 3 | Fireworks AI | $0.30 | $1.20 | - | 205K |
| MiniMax-M3.1-Flash | MiniMax | 3 | Fireworks AI | $0.15 | $0.60 | - | 1M |
| Mistral Large | Mistral AI | 3 | Mistral AI | $0.50 | $1.50 | - | 262K |
| Mistral Small 3.1 | Mistral AI | 3 | Google Cloud Vertex AI | $0.10 | $0.30 | 47% | 128K |
| mistral-small-3.2-24b-instruct-2506 | Mistral AI | 3 | DeepInfra | $0.075 | $0.20 | - | 128K |
| mixtral-8x7b-instruct | Mistral AI | 3 | Perplexity | $0.07 | $0.28 | - | 33K |
| mixtral-8x7b-instruct-v0.1 | Mistral AI | 3 | DeepInfra | $0.40 | $0.40 | 31% | 33K |
| MythoMax L2 13B | - | 3 | Novita AI | $0.09 | $0.09 | - | 4K |
| Nemotron Ultra | NVIDIA Nemotron | 3 | W&B Inference (CoreWeave) | $0.50 | $2.15 | - | 262K |
| Qwen3 30B A3B | Alibaba Qwen | 3 | Nebius Token Factory | $0.10 | $0.30 | 62% | 131K |
| Qwen3 VL 235B A22B Instruct | Alibaba Qwen | 3 | DeepInfra | $0.20 | $0.88 | - | 262K |
| qwen3-235b-a22b | Alibaba Qwen | 3 | DeepInfra | $0.18 | $0.54 | 71% | 262K |
| qwen3-235b-a22b-thinking-2507 | Alibaba Qwen | 3 | Fireworks AI | $0.22 | $0.88 | 80% | 262K |
| Qwen3-30B-A3B-Instruct-2507 | Alibaba Qwen | 3 | SiliconFlow | $0.09 | $0.30 | 56% | 262K |
| Qwen3-Coder-30B-A3B-Instruct | Alibaba Qwen | 3 | Novita AI | $0.07 | $0.27 | - | 262K |
| Qwen3-Next 80B-A3B Instruct | Alibaba Qwen | 3 | DeepInfra | $0.09 | $1.10 | - | 262K |
| Qwen3-VL-30B-A3B-Thinking | Alibaba Qwen | 3 | Fireworks AI | $0.15 | $0.60 | - | 262K |
| Qwen3-VL-8B-Instruct | Alibaba Qwen | 3 | Novita AI | $0.08 | $0.50 | - | 262K |
| Qwen3.5 9B | Alibaba Qwen | 3 | DeepInfra | $0.10 | $0.15 | 79% | 262K |
| Qwen3.7 Plus | Alibaba Qwen | 3 | Together AI | $0.32 | $1.28 | 88% | 1M |
| Beam 1.0 501B A23B | - | 2 | Together AI | $0.40 | $1.20 | - | 1M |
| chat | - | 2 | OpenAI | $5.00 | $30.00 | - | 400K |
| claude-3-5-haiku | Anthropic Claude | 2 | Amazon Bedrock | $0.80 | $4.00 | - | 200K |
| claude-3-5-sonnet | Anthropic Claude | 2 | Amazon Bedrock | $3.00 | $15.00 | - | 200K |
| claude-4-sonnet | Anthropic Claude | 2 | Replicate | $3.00 | $15.00 | - | 200K |
| claude-mythos-5-1 | Anthropic Claude | 2 | Anthropic | $10.00 | $50.00 | - | 1M |
| codellama-34b-instruct | Meta Llama | 2 | Perplexity | $0.35 | $1.40 | - | 16K |
| codellama-70b-instruct | Meta Llama | 2 | Fireworks AI | $0.90 | $0.90 | - | 16K |
| Codestral 25.01 | Mistral AI | 2 | Google Cloud Vertex AI | $0.20 | $0.60 | - | 256K |
| Command A | - | 2 | Oracle Cloud Generative AI | $1.56 | $1.56 | - | 256K |
| Command A Reasoning | - | 2 | Oracle Cloud Generative AI | $1.56 | $1.56 | - | 256K |
| Command A Translate | - | 2 | Oracle Cloud Generative AI | $0.09 | $0.09 | - | 256K |
| Command A Vision | - | 2 | Oracle Cloud Generative AI | $1.56 | $1.56 | - | 128K |
| Command R | - | 2 | Oracle Cloud Generative AI | $0.15 | $0.15 | - | 128K |
| Command R+ | - | 2 | Oracle Cloud Generative AI | $1.56 | $1.56 | - | 128K |
| DeepSeek R1 (Turbo) | DeepSeek | 2 | Novita AI | $0.70 | $2.50 | - | 64K |
| DeepSeek V4.1 Flash 1017 | DeepSeek | 2 | DeepSeek | $0.30 | $1.20 | - | 1M |
| deepseek-r1-distill-llama-8b | DeepSeek | 2 | Nscale | $0.025 | $0.025 | - | 131K |
| deepseek-r1-distill-qwen-1.5b | DeepSeek | 2 | Nscale | $0.09 | $0.09 | 34% | 131K |
| deepseek-r1-distill-qwen-7b | DeepSeek | 2 | Fireworks AI | $0.20 | $0.20 | - | 131K |
| DeepSeek-V3.2-Exp | DeepSeek | 2 | Novita AI | $0.27 | $0.41 | - | 164K |
| Gemini 2.5 Computer Use Preview 10-2025 | Google Gemini and Gemma | 2 | Google Gemini API | $1.25 | $10.00 | - | 128K |
| Gemini 2.5 Flash-Lite | Google Gemini and Gemma | 2 | Oracle Cloud Generative AI | $0.075 | $0.30 | - | 1M |
| Gemini 3 Flash Preview | Google Gemini and Gemma | 2 | Google Gemini API | $0.50 | $3.00 | 89% | 1M |
| Gemini 3.1 Pro Preview | Google Gemini and Gemma | 2 | Google Gemini API | $2.00 | $12.00 | 94% | 1M |
| Gemini 3.1 Pro Preview Custom Tools | Google Gemini and Gemma | 2 | Google Gemini API | $2.00 | $12.00 | - | 1M |
| Gemini 3.5 Flash Lite | Google Gemini and Gemma | 2 | Google Gemini API | $0.30 | $2.50 | 83% | 1M |
| Gemini 3.6 Flash | Google Gemini and Gemma | 2 | Google Gemini API | $0.75 | $3.75 | 94% | 1M |
| Gemini 3.8 Flash | Google Gemini and Gemma | 2 | Google Gemini API | $0.75 | $3.75 | 95% | 1M |
| Gemini 4 Argon | Google Gemini and Gemma | 2 | Google Gemini API | $2.00 | $10.00 | 96% | 1M |
| gemini-2.5-pro-preview-tts | Google Gemini and Gemma | 2 | Google Gemini API | $1.00 | $20.00 | - | 1M |
| gemini-omni-1.1-flash | Google Gemini and Gemma | 2 | Google Gemini API | $1.50 | $9.00 | - | 1M |
| gemini-robotics-er-2-preview | Google Gemini and Gemma | 2 | Google Gemini API | $1.00 | $5.00 | - | 131K |
| Gemma 3 4B IT | Google Gemini and Gemma | 2 | Amazon Bedrock | $0.04 | $0.08 | 23% | 131K |
| Gemma 4 31B IT | Google Gemini and Gemma | 2 | Amazon Bedrock | $0.14 | $0.40 | - | 262K |
| GLM 5.3 Fast | Z.ai GLM | 2 | Baseten | $2.10 | $6.60 | - | 1M |
| GLM-4.6V | Z.ai GLM | 2 | Z.ai | $0.30 | $0.90 | - | 131K |
| GLM-5-Turbo | Z.ai GLM | 2 | Z.ai | $1.20 | $4.00 | - | 203K |
| GPT OSS Safeguard 120B | OpenAI | 2 | Amazon Bedrock | $0.15 | $0.60 | - | 131K |
| GPT OSS Safeguard 20B | OpenAI | 2 | Amazon Bedrock | $0.07 | $0.20 | - | 131K |
| gpt-4.1-nano | OpenAI | 2 | Replicate | $0.10 | $0.40 | - | 1M |
| gpt-4o-audio-preview | OpenAI | 2 | OpenAI | $2.50 | $10.00 | - | 128K |
| gpt-4o-mini-audio-preview | OpenAI | 2 | OpenAI | $0.15 | $0.60 | - | 128K |
| GPT-5 Pro | OpenAI | 2 | OpenAI | $15.00 | $120.00 | - | 400K |
| GPT-5.1 | OpenAI | 2 | OpenAI | $1.25 | $10.00 | - | 272K |
| GPT-5.2 | OpenAI | 2 | OpenAI | $1.75 | $14.00 | - | 272K |
| GPT-5.3 Codex | OpenAI | 2 | OpenAI | $1.75 | $14.00 | - | 400K |
| GPT-5.4 mini | OpenAI | 2 | OpenAI | $0.75 | $4.50 | - | 272K |
| GPT-5.4 nano | OpenAI | 2 | OpenAI | $0.20 | $1.25 | - | 272K |
| GPT-5.4 Pro | OpenAI | 2 | OpenAI | $30.00 | $180.00 | - | 1.1M |
| GPT-5.6 | OpenAI | 2 | OpenAI | $4.00 | $20.00 | - | 922K |
| gpt-audio | OpenAI | 2 | OpenAI | $2.50 | $10.00 | - | 128K |
| gpt-audio-1.5 | OpenAI | 2 | OpenAI | $2.50 | $10.00 | - | 128K |
| gpt-audio-mini | OpenAI | 2 | OpenAI | $0.60 | $2.40 | - | 128K |
| granite-3-3-8b-instruct | - | 2 | Replicate | $0.03 | $0.25 | - | 8K |
| Grok 4.1 Fast (Non-Reasoning) | xAI Grok | 2 | Google Cloud Vertex AI | $0.20 | $0.50 | - | 128K |
| Grok 4.1 Fast (Reasoning) | xAI Grok | 2 | Google Cloud Vertex AI | $0.20 | $0.50 | - | 128K |
| grok-4 | xAI Grok | 2 | Microsoft Azure AI Foundry | $3.00 | $15.00 | - | 262K |
| grok-code-fast-1 | xAI Grok | 2 | Microsoft Azure AI Foundry | $0.20 | $1.50 | - | 256K |
| hermes-3-llama-3.1-405b | - | 2 | DeepInfra | $1.00 | $1.00 | - | 131K |
| Hy4 preview | - | 2 | DeepInfra | $0.834 | $2.50 | - | 1M |
| Kimi K3.1 Pro | Moonshot AI Kimi | 2 | Moonshot AI | $2.00 | $10.00 | - | 1M |
| Kimi K3.1 Pro Highspeed | Moonshot AI Kimi | 2 | Moonshot AI | $4.00 | $20.00 | - | 1M |
| kimi-k2-instruct-0905 | Moonshot AI Kimi | 2 | DeepInfra | $0.50 | $2.00 | - | 262K |
| l3.1-70b-euryale-v2.2 | - | 2 | DeepInfra | $0.85 | $0.85 | - | 131K |
| Ling 3.0 Flash | - | 2 | DeepInfra | $0.06 | $0.18 | - | 262K |
| llama-3.1-nemotron-70b-instruct | Meta Llama | 2 | DeepInfra | $0.60 | $0.60 | - | 131K |
| llama-v2-13b | Meta Llama | 2 | Replicate | $0.10 | $0.50 | - | 4K |
| llama-v2-13b-chat | Meta Llama | 2 | Replicate | $0.10 | $0.50 | - | 4K |
| llama-v2-70b | Meta Llama | 2 | Fireworks AI | $0.10 | $0.10 | - | 4K |
| llama-v2-7b | Meta Llama | 2 | Replicate | $0.05 | $0.25 | - | 4K |
| llama-v2-7b-chat | Meta Llama | 2 | Replicate | $0.05 | $0.25 | - | 4K |
| llama-v3-8b | Meta Llama | 2 | Replicate | $0.05 | $0.25 | - | 8K |
| MiMo-V2.5 | - | 2 | Novita AI | $0.168 | $0.336 | - | 1M |
| MiMo-V2.5-Pro | - | 2 | Novita AI | $0.522 | $1.04 | - | 1M |
| MiMo-V2.6-Flash | - | 2 | DeepInfra | $0.14 | $0.28 | - | 1M |
| MiMo-V2.6-Pro | - | 2 | DeepInfra | $0.43 | $0.87 | - | 1M |
| MiniMax M1 80K | MiniMax | 2 | Fireworks AI | $0.10 | $0.10 | - | 1M |
| Ministral 3B | Mistral AI | 2 | Microsoft Azure AI Foundry | $0.04 | $0.04 | - | 131K |
| ministral-3-14b-instruct-2512 | Mistral AI | 2 | Fireworks AI | $0.20 | $0.20 | - | 262K |
| Mistral Medium 3 | Mistral AI | 2 | Google Cloud Vertex AI | $0.40 | $2.00 | - | 262K |
| Mistral Small 3 | Mistral AI | 2 | DeepInfra | $0.05 | $0.08 | - | 33K |
| mistral-7b-instruct | Mistral AI | 2 | Perplexity | $0.07 | $0.28 | - | 32K |
| mistral-7b-instruct-v0.2 | Mistral AI | 2 | Replicate | $0.05 | $0.25 | - | 33K |
| mistral-7b-instruct-v0.3 | Mistral AI | 2 | OVHcloud AI Endpoints | $0.1117 | $0.1117 | 15% | 127K |
| mistral-large-2402 | Mistral AI | 2 | Amazon Bedrock | $4.00 | $12.00 | 39% | 32K |
| mistral-large-2407 | Mistral AI | 2 | Amazon Bedrock | $2.00 | $6.00 | 49% | 128K |
| mistral-large-3 | Mistral AI | 2 | Mistral AI | $0.50 | $1.50 | - | 262K |
| mistral-medium-3-5 | Mistral AI | 2 | Mistral AI | $1.50 | $7.50 | - | 262K |
| Muse Spark Open | - | 2 | Baseten | $1.25 | $4.25 | - | 1M |
| muse-glimmer-30b | - | 2 | DeepInfra | $0.30 | $1.20 | - | 131K |
| Nano Banana | Google Gemini and Gemma | 2 | Google Gemini API | $0.30 | $30.00 | - | 33K |
| Nano Banana 2 | Google Gemini and Gemma | 2 | Google Gemini API | $0.50 | $60.00 | - | 131K |
| Nano Banana 2 Lite | Google Gemini and Gemma | 2 | Google Gemini API | $0.25 | $30.00 | - | 66K |
| Nano Banana Pro | Google Gemini and Gemma | 2 | Google Gemini API | $2.00 | $120.00 | - | 66K |
| Nemotron 3 Nano 30B A3B | NVIDIA Nemotron | 2 | DeepInfra | $0.05 | $0.20 | - | 262K |
| Nemotron 3.5 Super VL | NVIDIA Nemotron | 2 | Baseten | $0.20 | $0.50 | - | 1M |
| nvidia-nemotron-nano-9b-v2 | NVIDIA Nemotron | 2 | DeepInfra | $0.04 | $0.16 | - | 131K |
| o1 | OpenAI | 2 | Replicate | $15.00 | $60.00 | - | 200K |
| o1-mini | OpenAI | 2 | Replicate | $1.10 | $4.40 | - | 128K |
| o3 | OpenAI | 2 | OpenAI | $2.00 | $8.00 | - | 200K |
| o4-mini | OpenAI | 2 | Replicate | $1.00 | $4.00 | - | 200K |
| Phi-4 | - | 2 | DeepInfra | $0.07 | $0.14 | 56% | 16K |
| Qwen Max | Alibaba Qwen | 2 | Alibaba Cloud Model Studio | $1.60 | $6.40 | - | 262K |
| Qwen-MT Plus | Alibaba Qwen | 2 | Novita AI | $0.25 | $0.75 | - | 16K |
| qwen-v2.5-14b-instruct | Alibaba Qwen | 2 | Fireworks AI | $0.20 | $0.20 | - | 33K |
| qwen2-vl-72b-instruct | Alibaba Qwen | 2 | Nebius Token Factory | $0.13 | $0.40 | - | 131K |
| qwen2-vl-7b-instruct | Alibaba Qwen | 2 | Nebius Token Factory | $0.02 | $0.06 | - | 131K |
| qwen2.5-32b-instruct | Alibaba Qwen | 2 | Nebius Token Factory | $0.06 | $0.20 | 46% | 128K |
| qwen2.5-coder-3b-instruct | Alibaba Qwen | 2 | Nscale | $0.01 | $0.03 | - | 33K |
| qwen2.5-coder-7b | Alibaba Qwen | 2 | Nebius Token Factory | $0.01 | $0.03 | - | 33K |
| qwen2.5-coder-7b-instruct | Alibaba Qwen | 2 | Nscale | $0.01 | $0.03 | - | 33K |
| qwen2.5-vl-32b-instruct | Alibaba Qwen | 2 | DeepInfra | $0.20 | $0.60 | - | 128K |
| Qwen3 30B A3b fp8 | Alibaba Qwen | 2 | Cloudflare Workers AI | $0.0509 | $0.335 | - | 41K |
| Qwen3 Coder Next | Alibaba Qwen | 2 | Novita AI | $0.20 | $1.50 | - | 262K |
| qwen3-32b-fp8 | Alibaba Qwen | 2 | Lambda | $0.05 | $0.10 | - | 131K |
| qwen3-4b | Alibaba Qwen | 2 | Nebius Token Factory | $0.08 | $0.24 | 52% | 41K |
| Qwen3-8B | Alibaba Qwen | 2 | SiliconFlow | $0.06 | $0.06 | 57% | 131K |
| qwen3-max | Alibaba Qwen | 2 | DeepInfra | $1.20 | $6.00 | - | 262K |
| qwen3-vl-235b-a22b-thinking | Alibaba Qwen | 2 | Fireworks AI | $0.22 | $0.88 | - | 262K |
| Qwen3-VL-32B-Instruct | Alibaba Qwen | 2 | SiliconFlow | $0.20 | $0.60 | - | 262K |
| Qwen3.6 Plus | Alibaba Qwen | 2 | Alibaba Cloud Model Studio | $0.50 | $3.00 | 88% | 1M |
| Step 3.7 Flash | - | 2 | DeepInfra | $0.20 | $1.15 | - | 262K |
| Step 5 Preview | - | 2 | DeepInfra | $1.00 | $2.70 | - | 1M |
| WizardLM 2 8x22B | - | 2 | DeepInfra | $0.48 | $0.48 | 43% | 66K |
Browse developer pages and curated price lists
See also recent price changes.